Skip to content
Model infoModelsSnapshot: 15 Oct 2026

NAVER Cloud / CLOVA Voice

CLOVA Voice Premium

Multilingual speech synthesis with 108 documented voice IDs, voice-specific emotion controls, and MP3 or WAV output.

Speech & voice
availableClosed weightsText-to-speech
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
9 of 22 specification fields collected
Text input limit2,000 characters: Korean, Japanese, Chinese, Taiwanese. 3,000 characters: English, Spanish.See specification notes below
Languages6 listedFull language list in specifications
Input billingNot collectedCLOVA Voice
Output billingNot collectedNo inferred price

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
AudioSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Korean, English, Japanese, Chinese, Spanish, TaiwaneseSource for Languages (opens in a new tab)

Language names follow the provider. Two voice IDs also support Korean plus U.S. English.

Context caching
Not collected
Maximum prompt characters
2,000 characters: Korean, Japanese, Chinese, Taiwanese. 3,000 characters: English, Spanish.Source for Maximum prompt characters (opens in a new tab)

The general prerequisites page still states 2,000 for every request. These language-specific limits come from the API reference; verify the live boundary when relying on more than 2,000. UTF-8 input required.

Output formats
MP3, WAVSource for Output formats (opens in a new tab)
Audio sample rates
WAV: 8, 16, 24 (default) or 48 kHz. The mijin voice supports only 16 kHz.Source for Audio sample rates (opens in a new tab)
Voice controls
Volume −5…5; speed −5…10 (negative is faster); pitch −5…5; tone alpha −5…5. Emotion and end-pitch controls depend on the voice.Source for Voice controls (opens in a new tab)
Request mode
Form-encoded text request returning binary speech audio. A live API request does not establish incremental audio streaming.Source for Request mode (opens in a new tab)
Usage metering
Pay-as-you-go plan with a base fee even when no calls are made. Numeric rates still need verification.Source for Usage metering (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

CLOVA Voice

Provider source (opens in a new tab)
API model ID
Not collected

This service exposes a dedicated route or workflow rather than a selectable checkpoint ID.

Access
NAVER Cloud application registration and client ID/secret required.
Regions
Korea, U.S., Singapore, Japan and Germany are listed as supported service environments. The common gateway does not establish customer-specific data residency.
API endpoint URL
POST https://naveropenapi.apigw.ntruss.com/tts-premium/v1/ttsSource for API endpoint URL (opens in a new tab)
Voice controls
Volume −5…5; speed −5…10 (negative is faster); pitch −5…5; tone alpha −5…5. Emotion and end-pitch controls depend on the voice.Source for Voice controls (opens in a new tab)
Output formats
MP3, WAVSource for Output formats (opens in a new tab)

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Live API use required. Generated-file reuse/resale and editing-service restrictions are documented; this policy is not a data-retention certification.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

CLOVA Voice

Not verified

Provider-side caching eligibility and rates have not been established for this service. A downloaded result or retained transcript is not prompt caching.

How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Voice choices

108 voices

Choose a voice within CLOVA Voice Premium. These are API voice identifiers, not additional model releases. Source links document each voice.

Published voice catalog
Voice / API IDLanguage & accentDelivery
Ara (angry)dara_angKoreanFemaleVoice source (opens in a new tab)
JinhojinhoKoreanMaleVoice source (opens in a new tab)
MijinmijinKoreanFemale. WAV output limited to 16 kHz.Voice source (opens in a new tab)
NeulbomnappleKoreanFemaleVoice source (opens in a new tab)
Ara (agent)nara_callKoreanFemaleVoice source (opens in a new tab)
AranaraKoreanFemale. Neutral, sad and happy emotion settings; angry not supported.Voice source (opens in a new tab)
BoranboraKoreanFemaleVoice source (opens in a new tab)
DaeseongndaeseongKoreanMaleVoice source (opens in a new tab)

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Inferred for this named native commercial model service from NAVER’s own API documentation and the reviewed public HyperCLOVA X inventory. No weights for this exact service were identified. This is a service-level identity, not a claim that its underlying checkpoint is disclosed or that every NAVER audio model is proprietary. Public SEED Omni remains excluded.

Classification evidence (opens in a new tab)

Sources reviewed